SAMT 2006 - Program

Conference Program

Wednesday, 6 December 2006

	Aristotelis A	Aristotelis B	Themistocles A	Themistocles B
09:30 - 11:00	LSAS	SEMPS	Tutorial 1
11:00 - 11:30	Coffee Break — Room: Lobby
11:30 - 13:00	LSAS	SEMPS	Tutorial 1
13:00 - 14:00	Lunch — Room: Aspasia
14:00 - 15:30	LSAS	SEMPS	Tutorial 2	Tutorial 3
15:30 - 16:00	Coffee Break — Room: Lobby
16:00 - 17:30	LSAS	SEMPS	Tutorial 2	Tutorial 3

Socrates
09:00 - 11:00	Industry Day
11:00 - 11:20	Coffee Break
11:20 - 13:00	Industry Day
13:00 - 14:00	Lunch
14:00 - 16:30	Industry Day

19:30 - 22:00	Cocktail Reception — Room: Lobby
19:30 - 22:00	Poster & Demo Session 1 — Room: Aristotelis A&B [ = Includes a demonstration]
	Mind the Gap - Requirements for the Combination of Content and Knowledge Tobias Buerger, Rupert Westenthaler Salzburg Research Forschungsgesellschaft, Austria Indexing Camera Motion with Knowledge Integration of the Quality of the Encoded Video Stream Petra Krämer, Jenny Benois-Pineau, Marta Gràcia Pla LaBRI, University of Bordeaux, France 3D Shape Annotation and Retrieval using Ontology Quang-Huy, Bui, Minh-Nam, Phuong Public Security Ministry, VietNam A Spatial Algebra for Multimedia Document Adaptation Sébastien Laborie, Jérôme Euzenat, Nabil Layaïda INRIA Rhône-Alpes, France Imaging Words – Wording Images Adrian Popescu, Gregory Grefenstette, Christophe Millet, Pierre-Alain Moëllic, Patrick Hède Commissariat à l'Energie Atomique, France Cepstral Polynomial Regression for Sequential Detection of Impulsive Waveform in Video Sound-track Cyril Hory, Laboratoire Traitement et Communication de l'Information, France William Christmas, University of Surrey, UK Anil Kokaram, University of Dublin, Trinity College, Ireland Semantic Human 3D Shapes Annotation for Animation Fabien Dellas, Laurent Moccozet, Nadia Magnenat-Thalmann, University of Geneva, Switzerland Giuseppe Patane, Michela Mortara, Michela Spagnuolo, Bianca Falcidieno IMATI CNR, Italy Living with the Semantic Gap: Experiences and Remedies in the Context of Medical Imaging Yannis Kalfoglou, Srinandan Dasmahapatra, David Dupplaw, Bo Hu, Paul Lewis, Nigel Shadbolt University of Southampton, UK Combining Color with Spatial and Temporal Position of the Endoscopic Capsule for Improved Topographic Classification and Segmentation Miguel Coimbra, Jacek Kustra, Paulo Campos, João Paulo Silva Cunha IEETA-Universidade de Aveiro, Portugal Exploiting Spatial Variability for Disparity Estimation Maria Trujillo, Universidad del Valle Ebroul Izquierdo, Queen Mary University of London, UK Using Context and a Genetic Algorithm for Knowledge-Assisted Image Analysis Stamatia Dasiopoulou, George Th. Papadopoulos, Aristotle University of Thessaloniki, Greece Phivos Mylonas, Yannis Avrithis, , National Technical University of Athens, Greece Ioannis Kompatsiaris, Informatics and Telematics Institute, Greece A multimodal approach to bridge the Music Semantic Gap Oscar Celma, Perfecto Herrera, Xavier Serra Universitat Pompeu Fabra, Barcelona, Spain Uncertainty Extensions to Ontologies as a Tool for Semantic Interpretation in Audiovisual Systems Pavel Smrz, Brno University of Technology, Czech Republic Miroslav Vacura, Ondrej Svab University of Economics, Prague, Czech Republic Semantically Exposing Existing Knowledge Repositories: A Case Study in Cultural Heritage Denis Pitzalis, Centre de Recherche et Restauration des Musées de France, France Patrick Sinclair, University of Southampton, UK Christian Lahanier, Centre de Recherche et Restauration des Musées de France, France Kirk Martinez, University of Southampton, UK Matthew Addis, IT Innovation Centre, UK Paul Lewis, University of Southampton, UK Richard Lowe, IT Innovation Centre, UK Shahbaz Hafeez, University of Southampton, UK Extensibility of Adaptation Capabilities in the CAIN Content Adaptation Engine Javier Molina, Jose M. Martinez, Victor Valdes, Fernando Lopez Universidad Autonoma de Madrid, Spain Using Local Region Semantics for Concept Detection in Video Evaggelos Spyrou, George Koumoulos, Yannis Avrithis, Stefanos Kollias National Technical University of Athens, Greece The Design of “intelligence” for the Management of Personal Multimedia Content Patricia Charlton, Jonathan Teh Motorola Labs, UK Evaluation of a Video Annotation Tool Based on the LSCOM Ontology Emilie Garnaud, Institut EURECOM, France Alan Smeaton, Markus Koskela Dublin City University, Ireland Connecting Foundational Ontologies with MPEG-7 Ontologies for Multimodal QA Massimo Romanelli, Daniel Sonntag, Norbert Reithinger DFKI, Germany Rule-based Reasoning for Semantic Image Segmentation and Interpretation Petr Berka, University of Economics, Prague, Czech Thanos Athanasiadis, Yannis Avrithis National Technical University of Athens, Greece A Framework for Integrating and Evaluating Automatic Region-based Segmentation Algorithms Kevin McGuinness, Gordon Keenan, Tomasz Adamek, Noel O'Connor Dublin City University, Ireland Automatic Text Searching for Personal Photos Neil O'Hare, Hyowon Lee, Saman Cooray, Cathal Gurrin, Gareth Jones, Jovanka Malobabic, Noel O'Connor, Alan Smeaton, Bartlomiej Uscilowski Dublin City University, Ireland Squiggle: A Semantic Search Engine at Work Irene Celino, Andrea Turati, Emanuele Della Valle, Dario Cerizza CEFRIEL Politecnico di Milano, Italy MediaMill: Video Search Using a Thesaurus of 500 Machine Learned Concepts Cees G.M. Snoek, Marcel Worring, Bouke Huurnink, Jan. C. van Gemert, Koen E.A. van de Sande, Dennis C. Koelma, Ork de Rooij University of Amsterdam, The Netherlands

Thursday, 7 December 2006

Room: Erechthion
08:30 - 09:15	Registration
09:15 - 09:30	Welcome
09:30 - 10:15	Content vs Context for Multimedia Semantics: The Case of SenseCam Image Structuring Invited keynote talk — Alan Smeaton Chair: Steffen Staab
10:15 - 10:45	Coffee Break — Room: Lobby
10:45 - 12:25	Oral Session 1: Semantic Multimedia Indexing Chair: Ebroul Izquierdo
	Image Clustering Using Multimodal Keywords Rajeev Agrawal, Kettering University, USA William Grosky, Wayne State University, USA Farshad Fotouhi, The University of Michigan - Dearborn, USA Personal Semantic Indexation of Images using Textual Annotations Gregory Smits, Michel Plu, Pascal Bellec France Telecom, France Image Classification using an Ant Colony Optimization approach Tomas Piatrik, Ebroul Izquierdo Queen Mary University of London, UK Extraction of Motion Activity from Scalable-coded Video Sequences Luis Herranz, Fabricio Tiburzi, Jesús Bescós Universidad Autonoma de Madrid, Spain
12:25 - 13:45	Lunch — Room: Aspasia
13:45 - 14:30	Bridging the Semantic Gap: Challenges from the Culture-Heritage Domain Invited keynote talk — Guus Schreiber Chair: Stefanos Kollias
14:30 - 14:45	Coffee Break — Room: Lobby
14:45 - 16:00	Oral Session 2: Multimedia Semantics Chair: Lynda Hardman
	A Scalable Framework for Multimedia Knowledge Management Yves Raimond, Samer Abdallah, Mark Sandler, Mounia Lalmas Queen Mary University of Lodnon, UK Enabling Multimedia Metadata Interoperability by Defining Formal Semantics of MPEG-7 Profiles Raphael Troncy, CWI Amsterdam, The Netherlands Werner Bailer, Michael Hausenblas, Philip Hofmair, Rudolf Schlatte Joanneum Research, Austria Trend Detection in Folksonomies Andreas Hotho, University of Kassel, Germany Robert Jäschke, Research Center L3S, Germany Christoph Schmitz, University of Kassel, Germany Gerd Stumme, Research Center L3S, Germany
16:00 - 16:30	Coffee Break — Room: Lobby
16:30 - 17:45	Oral Session 3: Semantic Multimedia Access and Retrieval Chair: Keith van Rijsbergen
	A Bayesian Network Approach to Multi-feature Based Image Retrieval Qianni Zhang, Ebroul Izquierdo Queen Mary University of London, UK Automated speech and audio analysis for semantic access to multimedia Franciska de Jong, TNO-ICT, Delft, The Netherlands Roeland Ordelman, Marijn Huijbregts University of Twente, The Netherlands An engine for content-aware on-line video adaptation Luis Herranz, Fabricio Tiburzi, Jesús Bescós Universidad Autonoma de Madrid, Spain

20:30 - 23:30	Conference Dinner

Friday, 8 December 2006

Room: Erechthion
09:15 - 09:30	Awards
09:30 - 10:15	From Intelligent Content to Actionable Knowledge: Research Directions and Opportunities under FP7 Invited talk — Roberto Cencioni Chair: Paola Hobson
10:15 - 10:45	Coffee Break — Room: Lobby
10:45 - 12:25	Special Session: Context-based Multimedia Analysis Chair: Yannis Avrithis
	Use of Image Regions in Context-Adaptive Image Classification Ville Viitaniemi, Jorma Laaksonen Helsinki University of Technology, Finland BPT Enhancement Based on Syntactic and Semantic Criteria Christian Ferran, Xavier Giro, Ferran Marques, Josep Ramon Casas Technical University of Catalonia, Barcelona, Spain Semantic image analysis using a learning approach and spatial context Georgios Th. Papadopoulos, Aristotle University of Thessaloniki, Greece Vasileios Mezaris, Informatics and Telematics Institute, Greece Stamatia Dasiopoulou, Aristotle University of Thessaloniki, Greece Ioannis Kompatsiaris, Informatics and Telematics Institute, Greece A Context-based Region Labeling Approach for Semantic Image Segmentation Thanos Athanasiadis, Phivos Mylonas, Yannis Avrithis National Technical University of Athens, Greece
12:25 - 14:30	Lunch — Room: Lobby
12:25 - 14:30	Special Poster & Demo Session: Projects — Room: Aristotelis B [ = Includes a demonstration]
	IP-Racine Metadata Implementation Integration in the Digital Cinema Workflow Josep Blat, University Pompeu Fabra, Italy Benoit Michel, XDC, Belgium Werner Haas, Joanneum Research Institute, Austria PATExpert: Semantic Processing of Patent Documentation Leo Wanner, ICREA and Foundation Barcelona Media, Spain Sören Brügmann, Industrie Software J. Brugmann, Germany, Barrou Diallo, European Patent Office Mark Giereth, University of Stuttgart, Germany Yiannis Kompatsiaris, Aristotle University of Thessaloniki, Greece Emanuele Pianta, ITC/IRST, Italy Gautam Rao, IALE, Spain Pia Schöster, Fraunhofer Gesellschaft, Germany EU-IST Project Live: Live Staging of Media Events Joachim Köhler, Fraunhofer IAIS, Germany Richard Wages, University of Applied Sciences Cologne, Germany Carmen Mac Williams, Academy of Media Arts (KHM), Germany Heike Fischer, Fraunhofer IAIS, Germany SALERO: Semantic Audiovisual Entertainment Reusable Objects Werner Haas, Georg Thallinger, Joanneum Research Institute, Austria Pedro Cano, Universitat Pompeu Fabra, Italy Charlie Cullen, Dublin Institute of Technology, Ireland Tobias Bürger, DERI at University of Innsbruck, Austria PHAROS: Platform for Search of Audiovisual Resources Across Online Spaces Stefan Debald, Fast Search & Transfer ASA (FAST), Norway Wolfang Nejdl, L3S Research Center, Germany Francesco Saverio Nucci, Engineering SpA, Italy Raluca Paiu, L3S Research Center, Germany Michel PluFrance Telecom R&D, France Multimedia Content Processing and Retrieval in the REVEAL THIS Setting Stelios Piperidis, Harris Papageorgiou, Katerina Pastra, Institute of Language and Speech Processing, Greece Thomas Netousek, SAIL Labs Technology AG Eric Gaussier, Xerox - The Document Company Tinne Tuytelaars, Katholieke Universiteit Leuven R&D Fabio Crestani, University of Strathclyde Francis Bodson, BeTV SA, UK An Overview of the PENG Project Gabriella Pasi, DISCO, Università degli Studi di Milano Bicocca, Milano, Italy Gloria Bordogna, IDPA, Consiglio Nazionale delle Ricerche, Dalmine (Bg), Italy X-Media: Large Scale Knowledge Acquisition, Sharing and Reuse Across-Media Fabio Ciravegna, University of Sheffield, UK Steffen Staab, University of Koblenz-Landau, Germany AIM@SHAPE: Research Advantages and Future Contributions Bianca Falcidieno, Michela Spagnuolo, CNR, Institute of Applied Mathematics and Information Technology Marios Pitikakis, George Vasilakis, Informatics and Telematics Institute, Greece Alejandra Garcia-Rojas, Laura Papaleo DISI, Università di Genova, Italy Personal Navigation in the World of News Nikos Sarris, ATC, Greece Paulo Villegas, Telefonica I+D, Spain Martin Pinkerneil, Jochen Spangenberg, Deutsche Welle, Germany Jérôme Picault, Motorola SAS, France An Approach to Self-Annotating Content Adrian Matellanes, Motorola Ltd., UK Freddy Snijder, Philips Research, The Netherlands Barbara Schmidt-BelzFraunhofer-FIT, Germany Knowledge Space of Semantic Inference for Automatic Annotation and retrieval of Multimedia Content – K-Space Craig Stewart, Ebroul Izquierdo Queen Mary University of London, UK Semantics Extraction from Multimedia Content: The BOEMIE Architecture Sergios Petridis, Nicolas Tsapatsoulis
14:30 - 15:15	Networked Audiovisual Systems: R&D for the Birth of a New Sector in Europe Invited talk — Luis Rodriguez-Rosello Chair: Jose M. Martinez
15:15 - 15:45	Coffee Break — Room: Lobby
15:45 - 17:00	Oral Session 4: Towards 3D in Semantic Multimedia Chair: Paul Lewis
	In Search for your own Virtual Individual Laurent Moccozet, MIRALab, University of Geneva, Switzerland Alejandra Garcia-Rojas, Frédéric Vexo, Daniel Thalmann, VRLab, EPFL, Lausanne, Switzerland Nadia Magnenat-Thalmann, MIRALab, University of Geneva, Switzerland Human Activity Language: Grounding Concepts with a Linguistic Framework Gutemberg Guerra-Filho, Yiannis Aloimonos University of Maryland, USA A Probability-based Unified 3D Shape Search Suyu Hou, Karthik Ramani Purdue University, USA